Skip to content

Offloading Bug Fix #58

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Aug 6, 2024
Merged

Offloading Bug Fix #58

merged 2 commits into from
Aug 6, 2024

Conversation

Satrat
Copy link
Contributor

@Satrat Satrat commented Aug 6, 2024

SUMMARY:
Fixes for two issues that came up during testing

  • Missing fstring for an assertion being raised
  • sparsity structure calculation fails for offloaded models. We missed this bug because this check gets skipped for models with < 5% sparsity

TEST PLAN:
Manual testing

@Satrat Satrat merged commit 066d1e4 into main Aug 6, 2024
7 of 12 checks passed
@Satrat Satrat deleted the sa/offload_fix branch August 6, 2024 15:09
@Satrat Satrat mentioned this pull request Aug 6, 2024
markmc pushed a commit to markmc/llm-compressor that referenced this pull request Nov 13, 2024
* initial commit

* check device types when quant

* fix forward

* another fix

* Update src/compressed_tensors/quantization/lifecycle/apply.py

* beautify

* attempt fix tests

* add warning for undetected ignored modules

* refactor

* Remove the dot

---------

Co-authored-by: [email protected] <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant